--- title: "Independent Testers Disturbed by Results When They Drive Tesla FSD for 1,000 Miles" description: "Researchers at the independent firm AMCI Testing found that Full Self-Driving required human intervention at an alarmingly high rate." date: "2024-09-27" modified: "2024-09-27" authors: - name: "Frank Landymore" job_title: "Contributing Writer" link: "https://futurism.com/authors/flandymore" url: "https://futurism.com/the-byte/testers-disturbed-tesla-fsd" categories: - "Advanced Transport" - "Tesla" tags: - "full self-driving" - "robotaxis" - "tesla" - "the digest" --- # Independent Testers Disturbed by Results When They Drive Tesla FSD for 1,000 Miles ![Researchers at the independent firm AMCI Testing found that Full Self-Driving required human intervention at an alarmingly high rate.]() *\Image: ACMI Testing via YouTube\* ## Benign Intervention A team of researchers at the independent firm AMCI Testing drove a Tesla in [Full-Self Driving mode]() for over 1,000 miles, finding its capabilities to be "suspect" at best — because of dangerous and unpredictable infractions like running a red light. They walked away unconvinced that the system, although impressive in some respects, is ready to be fully autonomous — a rebuff to Tesla CEO Elon Musk's ambitions of [launching a driverless robotaxi service](). According to the firm, its testers were forced to intervene over 75 times while Full Self-Driving was in control. On average, that's once every 13 miles. Given that the typical driver in the US travels about [35 to 40 miles per day](), that's an alarmingly frequent rate of requiring human intervention. "What's most disconcerting and unpredictable is that you may watch FSD successfully negotiate a specific scenario many times — often on the same stretch of road or intersection — only to have it inexplicably fail the next time," AMCI director Guy Mangiamele said in a [statement](). ## Road Warrior As shown in three videos [summing up the findings](), Full Self-Driving did manage several types of scenarios admirably. In one [instance](), in which a Tesla was driving down a tight, two-way road lined with parked cars, the vehicle cleverly pulled into a gap on the right hand side to allow oncoming traffic to pass. But in an activity where safety *should* be paramount, Full Self-Driving needs to be next to flawless. It definitely was not that. During a [night drive in the city](), the Tesla with the driving mode engaged [straight-up ran a red light]() that was clearly visible, seemingly because it was following other motorists who also disregarded the light. In another [dangerous scenario](), Full Self-Driving failed to either recognize or follow a double yellow line around a curve. The Tesla veered into oncoming traffic, and only avoided a potential collision after the driver intervened. (This is almost exactly what Musk experienced first-hand [way back in *2015*](), and it's still an issue now.) ## Taxi Truths Musk has teased the launch of a [driverless robotaxi service](), which would reportedly use a new vehicle that fans have nicknamed the "[Cybercab]()." Yet if AMCI's testing is anything to go by, the company's autonomous driving tech may not be safe enough for the task. It's unclear, though, how its safety record would stack up against the capabilities of competitors like Waymo, a veteran in the robotaxi industry. But even with a human behind the wheel, Full Self-Driving poses significant risks, according to Mangiamele, because it "breeds a sense of awe that unavoidably leads to dangerous complacency." "When drivers are operating with FSD engaged, driving with their hands in their laps or away from the steering wheel is incredibly dangerous," he added. "As you will see in the videos, the most critical moments of FSD miscalculation are split-second events that even professional drivers, operating with a test mindset, must focus on catching." **More on Tesla:** *[Workers Training Tesla’s Autopilot Say They Were Told to Ignore Road Signs to Avoid Making Cars Drive Like a "Robot"]()* ## Author At Futurism, my work has often centered on bringing a sense of clarity and insight to complex topics ranging from the regulation of emerging technologies to the esoteric ideologies of Silicon Valley executives, while striving not to lose the poetic sense of awe inspired by often-obscure fields like astrophysics and quantum computing. I broke the story of CNET using AI to produce articles that turned out to be riddled with factual errors and plagiarism — a dam-breaking inflection point, as I've reported, that's inspired copycats and endless discourse while beguiling stakeholders ranging from tech giants to purveyors of spam around the web. My work at Futurism has been cited by publications including CBS News, the Los Angeles Times, Vice, Gizmodo, Engadget, the Verge, and Vanity Fair. I grew up in locales ranging from India to China, and now live in the exotic suburbs of Virginia. In my free time, I'm an avid reader of weird sci-fi literature, an aficionado of East Asian cinema, and, regrettably, a relapsed gamer. Allegedly, I’m working on a debut novel, currently untitled. ### Author social links [Bluesky]()